Ziqi Zhou

Early detection of failure in LLM agents can save over 47% of inference compute by leveraging internal representations rather than observable behavior.

Achieving stable adversarial camouflage in dynamic environments, VFACamou reduces human detection rates while preserving natural appearance, a breakthrough for physical evasion tactics.

LEADS enables the automated discovery of personalized cardiac models, outperforming expert-designed approaches and setting a new standard for stability in cardiac simulations.